]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/njpwworld.py
2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
7 from ..compat
import compat_urlparse
15 class NJPWWorldIE(InfoExtractor
):
16 _VALID_URL
= r
'https?://njpwworld\.com/p/(?P<id>[a-z0-9_]+)'
17 IE_DESC
= '新日本プロレスワールド'
18 _NETRC_MACHINE
= 'njpwworld'
21 'url': 'http://njpwworld.com/p/s_series_00155_1_9/',
23 'id': 's_series_00155_1_9',
25 'title': '第9試合 ランディ・サベージ vs リック・スタイナー',
29 'skip_download': True, # AES-encrypted m3u8
31 'skip': 'Requires login',
34 _LOGIN_URL
= 'https://front.njpwworld.com/auth/login'
36 def _real_initialize(self
):
40 username
, password
= self
._get
_login
_info
()
41 # No authentication to be performed
45 # Setup session (will set necessary cookies)
46 self
._request
_webpage
(
47 'https://njpwworld.com/', None, note
='Setting up session')
49 webpage
, urlh
= self
._download
_webpage
_handle
(
50 self
._LOGIN
_URL
, None,
51 note
='Logging in', errnote
='Unable to login',
52 data
=urlencode_postdata({'login_id': username
, 'pw': password
}),
53 headers
={'Referer': 'https://front.njpwworld.com/auth'})
54 # /auth/login will return 302 for successful logins
55 if urlh
.geturl() == self
._LOGIN
_URL
:
56 self
.report_warning('unable to login')
61 def _real_extract(self
, url
):
62 video_id
= self
._match
_id
(url
)
64 webpage
= self
._download
_webpage
(url
, video_id
)
67 for mobj
in re
.finditer(r
'<a[^>]+\bhref=(["\'])/player
.+?
[^
>]*>', webpage):
68 player = extract_attributes(mobj.group(0))
69 player_path = player.get('href
')
72 kind = self._search_regex(
73 r'(low|high
)$
', player.get('class') or '', 'kind
',
75 player_url = compat_urlparse.urljoin(url, player_path)
76 player_page = self._download_webpage(
77 player_url, video_id, note='Downloading player page
')
78 entries = self._parse_html5_media_entries(
79 player_url, player_page, video_id, m3u8_id='hls
-%s' % kind,
80 m3u8_entry_protocol='m3u8_native
')
81 kind_formats = entries[0]['formats
']
82 for f in kind_formats:
83 f['quality
'] = 2 if kind == 'high
' else 1
84 formats.extend(kind_formats)
86 self._sort_formats(formats)
88 post_content = get_element_by_class('post
-content
', webpage)
90 r'<li
[^
>]+class="tag-[^"]+"><a[^>]*>([^<]+)</a></li>', post_content
91 ) if post_content else None
95 'title': self._og_search_title(webpage),